bmad-orchestrator — BMAD Workflow Orchestration with SSD

T → Task:     Decompose the phase into concrete tasks with assigned agents
E → Execute:  Run tasks in parallel via multi-agent team execution
A → Architect: Validate outputs for coherence, completeness, and cross-phase traceability

npx skills add https://github.com/akillness/oh-my-skills --skill bmad-orchestrator

/workflow-init [--ssd]
/workflow-status

/workflow-init --ssd
       |
       v
  ┌─────────────────────────────────────────────────────┐
  │              PHASE N TEA CYCLE                      │
  │                                                     │
  │  /ssd-decompose  (or /ssd-cycle for full auto)      │
  │       |                                             │
  │       v                                             │
  │  [T] Task decomposition                             │
  │       planner/analyst produces task list            │
  │       → ssd-state.json phases[N].tasks updated      │
  │       |                                             │
  │       v                                             │
  │  /ssd-execute                                       │
  │       |                                             │
  │       v                                             │
  │  [E] Multi-agent execution via /team                │
  │       TeamCreate → TaskCreate per subtask           │
  │       Agents: executor, analyst, designer,          │
  │               test-engineer, security-reviewer…     │
  │       → docs/ssd/phase-N/ artifacts produced        │
  │       → Phase document assembled from artifacts     │
  │       |                                             │
  │       v                                             │
  │  /ssd-validate                                      │
  │       |                                             │
  │       v                                             │
  │  [A] Architect validation                           │
  │       fabric -p bmad_ssd_phase_review               │
  │       (fallback: architect agent via TaskCreate)    │
  │       |                                             │
  │       ├── PASS ──────────→ plannotator review       │
  │       │                         |                   │
  │       │                    ┌────┴────┐              │
  │       │                    │ Approve │ Req Changes  │
  │       │                    └────┬────┘     |        │
  │       │                         |     Loop to [E]   │
  │       │                         v     with feedback │
  │       │                    /ssd-advance              │
  │       │                    → phase N+1               │
  │       │                                             │
  │       ├── PASS_WITH_WARNINGS → plannotator (warned) │
  │       │                                             │
  │       ├── REVISE → targeted re-execute specific     │
  │       │             tasks, then re-validate         │
  │       │                                             │
  │       └── FAIL → full re-execute with changes,      │
  │                   then re-validate                  │
  │                   (max 3 cycles, then escalate)     │
  └─────────────────────────────────────────────────────┘

mkdir -p ~/.config/fabric/patterns/bmad_ssd_phase_review
cat > ~/.config/fabric/patterns/bmad_ssd_phase_review/system.md << 'EOF'
# IDENTITY AND PURPOSE

You are an expert system architect performing a structured phase review for the BMAD Structured System Design (SSD) framework. Your job is to validate that a phase document is internally coherent, externally consistent with prior phase artifacts, and complete enough to advance to the next phase.

Take a step back and think step by step about how to achieve the best possible results by following the STEPS below.

# STEPS

1. IDENTIFY the current BMAD phase (Analysis, Planning, Solutioning, Implementation) from the input metadata.

2. PARSE the phase document and extract all claims, requirements, design decisions, and deliverables.

3. INTERNAL COHERENCE CHECK:
   - Are there contradictory statements within the document?
   - Are all sections complete (no TODOs, placeholders, or TBDs)?
   - Do quantitative claims have justification?

4. CROSS-PHASE TRACEABILITY CHECK (if prior phase artifacts are provided):
   - Phase 2 (Planning): Does every PRD requirement trace to a product brief goal?
   - Phase 3 (Solutioning): Does the architecture address every PRD functional requirement?
   - Phase 4 (Implementation): Does every story map to an architecture component?
   - Flag any orphaned items.

5. COMPLETENESS CHECK against BMAD level expectations:
   - Level 0-1: Minimal viable coverage
   - Level 2: Full requirement coverage with acceptance criteria
   - Level 3: Comprehensive with integration points and risk analysis
   - Level 4: Enterprise-grade with security, performance, and infrastructure coverage

6. RISK ASSESSMENT:
   - Identify assumptions that could invalidate the phase output
   - Flag unresolved dependencies
   - Note scope creep relative to prior phase boundaries

7. PRODUCE a structured verdict.

# OUTPUT INSTRUCTIONS

- Output valid Markdown only.
- Begin with a `## Verdict` section: one of `PASS`, `PASS_WITH_WARNINGS`, `FAIL`, or `REVISE`.
- Follow with `## Internal Coherence` (findings with line references).
- Follow with `## Cross-Phase Traceability` (coverage matrix if applicable).
- Follow with `## Completeness` (missing sections or underspecified areas).
- Follow with `## Risks` (ranked by severity: critical, high, medium, low).
- Follow with `## Required Changes` (concrete, actionable items if verdict is FAIL or REVISE).
- Do not include warnings, disclaimers, or caveats outside the structured sections.

# INPUT

INPUT:
EOF

# Pipe current phase doc + prior artifacts for cross-phase validation
{
  echo "--- CURRENT PHASE DOCUMENT ---"
  cat "$CURRENT_DOC"
  echo "--- PRIOR PHASE ARTIFACTS ---"
  for prior in "${PRIOR_DOCS[@]}"; do
    echo "--- $(basename "$prior") ---"
    cat "$prior"
  done
} | fabric -p bmad_ssd_phase_review --stream > docs/ssd/phase-N/architect-review.md

# Phase 3 example: validate architecture against PRD
cat docs/architecture-myapp-2026-03-16.md | \
  fabric -p bmad_ssd_phase_review \
  --context "$(cat docs/prd-myapp-2026-03-16.md)" \
  --stream

# In Claude Code session:
ssd validate — run architect review on the current phase document before advancing

{
  "version": "1.0.0",
  "project_name": "myapp",
  "project_level": 2,
  "active": true,
  "current_phase": 2,
  "created_at": "2026-03-16T10:00:00Z",
  "updated_at": "2026-03-16T14:30:00Z",
  "phases": {
    "1": {
      "name": "analysis",
      "tea_step": "complete",
      "tasks": {
        "decomposed_at": "2026-03-16T10:05:00Z",
        "items": [
          {
            "id": "p1-t1",
            "name": "Market research",
            "agent": "document-specialist",
            "model": "sonnet",
            "status": "completed",
            "output_path": "docs/ssd/phase-1/market-research.md"
          }
        ]
      },
      "architect_review": {
        "verdict": "PASS",
        "method": "fabric",
        "pattern": "bmad_ssd_phase_review",
        "report_path": "docs/ssd/phase-1/architect-review.md",
        "reviewed_at": "2026-03-16T11:00:00Z"
      },
      "plannotator_review": {
        "status": "approved",
        "reviewed_at": "2026-03-16T11:30:00Z",
        "document_hash": "abc123"
      }
    },
    "2": {
      "name": "planning",
      "tea_step": "execute",
      "tasks": {
        "items": [
          {
            "id": "p2-t1",
            "name": "Functional requirements extraction",
            "agent": "analyst",
            "model": "opus",
            "status": "in_progress"
          }
        ]
      },
      "architect_review": null,
      "plannotator_review": null
    }
  },
  "cross_phase_traceability": {
    "phase_1_to_2": { "validated": true, "coverage": 1.0, "orphaned_items": [] },
    "phase_2_to_3": { "validated": false },
    "phase_3_to_4": { "validated": false }
  }
}

# After /prd → docs/prd-myapp-2026-03-16.md is created
# With SSD: run /ssd-validate first, then phase-gate-review.sh
bash scripts/phase-gate-review.sh docs/prd-myapp-2026-03-16.md "PRD Review: myapp"

# After /architecture → docs/architecture-myapp-2026-03-16.md is created
bash scripts/phase-gate-review.sh docs/architecture-myapp-2026-03-16.md "Architecture Review: myapp"

# In Claude Code after /prd completes:
planno — review the PRD before we proceed to Phase 3

/prd completes → docs/prd-myapp.md created
       ↓
 /ssd-validate runs (automated architect review)
       ↓ fabric -p bmad_ssd_phase_review
       ↓
  PASS/PASS_WITH_WARNINGS?
       ↓ yes
 phase-gate-review.sh opens plannotator UI
       ↓
  [Approve]              [Request Changes]
       ↓                        ↓
 Obsidian saved          Agent revises doc
 ssd-state updated       /ssd-execute (targeted)
                         then /ssd-validate again
       ↓
 /ssd-advance → Phase 3

# Trigger SSD execution for current phase (Claude Code)
ssd execute — run phase 2 planning tasks with multi-agent team

/team 4:analyst "Execute BMAD Phase 2 planning: functional requirements, non-functional requirements, user stories, acceptance criteria based on product brief at docs/product-brief-myapp.md"

# 1. Initialize BMAD with SSD enabled
/workflow-init --ssd

# 2. Run full TEA cycle for Phase 1 (Analysis)
/ssd-cycle

# 3. Check status after cycle
/ssd-status

# 4. When architect validates PASS, human review opens automatically
# (plannotator UI launches)

# 5. After approval, advance to Phase 2
/ssd-advance

# 6. Repeat for each phase
/ssd-cycle  # Phase 2: Planning
/ssd-cycle  # Phase 3: Solutioning
/ssd-cycle  # Phase 4: Implementation

---
created: 2026-03-16T10:00:00Z
source: plannotator
tags: [bmad, ssd, phase-2, prd, myapp]
ssd_architect_verdict: PASS
ssd_tea_cycle: 1
---

[[BMAD Plans]]

# PRD: myapp
...